How to Use the Dify MCP in Claude

Q: How do I connect Dify to Claude Desktop?

Open your claudedesktopconfig.json file. Add the Dify MCP server configuration to your mcpServers block with your API key, save, and restart Claude Desktop.

Q: How does Claude Desktop handle Dify file uploads?

When you execute the uploadfile tool, Claude Desktop reads the file from your local disk. It then sends it as a multipart request directly to Dify's servers.

Q: Can I rate agent responses using this integration?

Yes, you can. The feedback tool lets you submit positive or negative ratings directly from your workspace, which helps align your production models over time.

Q: Where does my Dify chat history data go?

All session history, including text logs from listmessages and uploaded files, goes straight to your self-hosted or cloud Dify instance. Vinkius runs this server in an ephemeral, zero-trust sandbox, meaning we never cache or store your chat payloads.

Control Dify agentic workflows directly from Claude Desktop to run chats, manage history, and upload files using this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dify MCP to Claude Desktop

Create your Vinkius account to connect Dify to Claude Desktop and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Dify with Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Drive Dify chats directly inside Claude Desktop

Your local Claude Desktop app can now run full conversational workflows via the `chat` tool. This means you don't need to jump back and forth between different browser tabs to test your Dify agents. The tool connects straight to your Dify endpoints. It handles the message payload, runs the model on the backend, and returns the response directly into your active Claude workspace.

Audit past conversations with this MCP Server

Tracking down old context is annoying when you are debugging. Use `list_conversations` and `list_messages` to pull the exact execution logs from your Dify instance right into your chat. You can quickly inspect previous runs to see where an agent deviated. Having this telemetry inside your workspace makes fixing logic errors much faster.

Upload assets and submit feedback on the fly

Sending documents to your backend agent is simple with the `upload_file` tool. Claude Desktop routes files from your local machine straight to Dify's storage layer. If the agent's response misses the mark, trigger the `feedback` tool to log performance metrics. You can also pull configuration details using `get_parameters` to check which variables are active.

Setup guide

Set up Dify MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The Dify MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the Dify MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under dify-mcp.

json

{
  "mcpServers": {
    "dify-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Dify. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Dify now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Dify MCP in Claude Desktop

Open your claude_desktop_config.json file. Add the Dify MCP server configuration to your mcpServers block with your API key, save, and restart Claude Desktop.

Yes, you can plug the remote server URL directly into the Integrations settings in Claude Web. This allows you to run tools like `chat` and `upload_file` from any browser on any machine.

When you execute the `upload_file` tool, Claude Desktop reads the file from your local disk. It then sends it as a multipart request directly to Dify's servers.

Yes, you can. The `feedback` tool lets you submit positive or negative ratings directly from your workspace, which helps align your production models over time.

All session history, including text logs from `list_messages` and uploaded files, goes straight to your self-hosted or cloud Dify instance. Vinkius runs this server in an ephemeral, zero-trust sandbox, meaning we never cache or store your chat payloads.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript